My mind is already spinning excuses on overdrive.
As a teenager I spent 7 years in military school. They adopted the army ethos that if something under your responsibility goes wrong, you get punished. Regardless of whether you could have done anything about it. Trying to produce excuses usually led to being cut off with “I don’t care” followed by increasing the punishment.
This had an interesting effect—if you know you are going to be punished regardless of excuses, you stop thinking about excuses and start trying to head off problems. It’s like the Karate Kid approach to teaching murphyjitsu. From “you can’t possibly blame me for the rain” to “hey, what’s our backup plan if it rains during training”.
It could have equally gone the other way into learned helplessness though, so I don’t know whether it’s a good approach. But perhaps that refocusing could be achieved in other ways? Maybe simply making a rule of never offering excuses—just apologise, make reparations / accept punishment and move on.
(Posting here rather than SSC because I wrote the whole comment in markdown before remembering that SSC doesn’t support it).
We had a guest lecture from Friston last year and I cornered him afterwards to try to get some enlightenment (notes here). I also spent the next few days working through the literature, using a multi-armed bandit bandit as a concrete problem (notes here ).
Very few of the papers have concrete examples. Those that do often skip important parts of the math and use inconsistent/ambiguous notation. He doesn’t seem to have released any of the code for his game-playing examples.
The various papers don’t all even implement the same model—the free energy principle seems to be more a design principle than a specific model.
The wikipedia page doesn’t explain much but at least uses consistent and reasonable notation.
Reinforcement learning or active inference has most of a worked model, and is the closest I’ve found to explaining how utility functions get encoded into meta-priors. It also contains:
I am leaning towards ‘the emperor has no clothes’. In support of this:
Friston doesn’t explain things well, but nobody else seems to have produced an accessible worked example either, even though many people claim to understand the theory and think that is important.
Nobody seems to have has used this to solve any novel problems, or even to solve well-understood trivial problems.
I can’t find any good mappings/comparisons to existing models. Are there priors that cannot be represented as utility functions, or vice versa? What explore/exploit tradeoffs do free-energy models lead to, or can they encode any given tradeoff?
At this point I’m unwilling to invest any further effort into the area, but I could be re-interested if someone were to produce a python notebook or similar with a working solution for some standard problem (eg multi-armed bandit).